Error analysis and the role of morphology

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Error analysis and the role of morphology. / Bollmann, Marcel; Søgaard, Anders.

EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics, 2021. p. 1887-1900.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Bollmann, M & Søgaard, A 2021, Error analysis and the role of morphology. in EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics, pp. 1887-1900, 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021, Virtual, Online, 19/04/2021. <https://aclanthology.org/2021.eacl-main.162/>

APA

Bollmann, M., & Søgaard, A. (2021). Error analysis and the role of morphology. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 1887-1900). Association for Computational Linguistics. https://aclanthology.org/2021.eacl-main.162/

Vancouver

Bollmann M, Søgaard A. Error analysis and the role of morphology. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics. 2021. p. 1887-1900

Author

Bollmann, Marcel ; Søgaard, Anders. / Error analysis and the role of morphology. EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics, 2021. pp. 1887-1900

Bibtex

@inproceedings{1b5da8b8090c4724bd7d07a73902120b,
title = "Error analysis and the role of morphology",
abstract = "We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language. We show across four different tasks and up to 57 languages that of these conjectures, somewhat surprisingly, only (i) is true. Using morphological features does improve error prediction across tasks; however, this effect is less pronounced with morphologically complex languages. We speculate this is because morphology is more discriminative in morphologically simple languages. Across all four tasks, case and gender are the morphological features most predictive of error.",
author = "Marcel Bollmann and Anders S{\o}gaard",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics; 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 ; Conference date: 19-04-2021 Through 23-04-2021",
year = "2021",
language = "English",
pages = "1887--1900",
booktitle = "EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics",

}

RIS

TY - GEN

T1 - Error analysis and the role of morphology

AU - Bollmann, Marcel

AU - Søgaard, Anders

N1 - Publisher Copyright: © 2021 Association for Computational Linguistics

PY - 2021

Y1 - 2021

N2 - We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language. We show across four different tasks and up to 57 languages that of these conjectures, somewhat surprisingly, only (i) is true. Using morphological features does improve error prediction across tasks; however, this effect is less pronounced with morphologically complex languages. We speculate this is because morphology is more discriminative in morphologically simple languages. Across all four tasks, case and gender are the morphological features most predictive of error.

AB - We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language. We show across four different tasks and up to 57 languages that of these conjectures, somewhat surprisingly, only (i) is true. Using morphological features does improve error prediction across tasks; however, this effect is less pronounced with morphologically complex languages. We speculate this is because morphology is more discriminative in morphologically simple languages. Across all four tasks, case and gender are the morphological features most predictive of error.

M3 - Article in proceedings

AN - SCOPUS:85107267336

SP - 1887

EP - 1900

BT - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics

T2 - 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021

Y2 - 19 April 2021 through 23 April 2021

ER -

ID: 283136052